Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1141 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.2351. Min Range: -5.2351

Max Act: 5.2351. Min Act: -0.1700

Data Index: 963254 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 5.2351. Min Range: -5.2351

Max Act: 5.0163. Min Act: -0.1700

Data Index: 893805 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 5.2351. Min Range: -5.2351

Max Act: 5.0163. Min Act: -0.1700

Data Index: 1130076 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 5.2351. Min Range: -5.2351

Max Act: 4.9226. Min Act: -0.1700

Data Index: 98978 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 5.2351. Min Range: -5.2351

Max Act: 4.9538. Min Act: -0.1700

Data Index: 629115 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 5.2351. Min Range: -5.2351

Max Act: 4.9538. Min Act: -0.1700

Data Index: 1152890 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 5.2351. Min Range: -5.2351

Max Act: 4.9851. Min Act: -0.1700

Data Index: 416300 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 5.2351. Min Range: -5.2351

Max Act: 4.9538. Min Act: -0.1700

Data Index: 375973 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 5.2351. Min Range: -5.2351

Max Act: 4.9538. Min Act: -0.1700

Data Index: 249809 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 5.2351. Min Range: -5.2351

Max Act: 4.9538. Min Act: -0.1700

Data Index: 2474 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 5.2351. Min Range: -5.2351

Max Act: 4.8913. Min Act: -0.1700

Data Index: 888631 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 5.2351. Min Range: -5.2351

Max Act: 4.8601. Min Act: -0.1700

Data Index: 169990 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 5.2351. Min Range: -5.2351

Max Act: 4.8913. Min Act: -0.1700

Data Index: 937234 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 5.2351. Min Range: -5.2351

Max Act: 4.9226. Min Act: -0.1700

Data Index: 533859 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 5.2351. Min Range: -5.2351

Max Act: 4.8601. Min Act: -0.1700

Data Index: 844894 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 5.2351. Min Range: -5.2351

Max Act: 4.7976. Min Act: -0.1700

Data Index: 1066607 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 5.2351. Min Range: -5.2351

Max Act: 4.8288. Min Act: -0.1700

Data Index: 170572 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 5.2351. Min Range: -5.2351

Max Act: 4.8288. Min Act: -0.1700

Data Index: 134414 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 5.2351. Min Range: -5.2351

Max Act: 4.8913. Min Act: -0.1700

Data Index: 992627 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 5.2351. Min Range: -5.2351

Max Act: 4.7976. Min Act: -0.1700

Data Index: 842463 (C4 (Web Text))

Max Activating Token Index: 369